| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.007682851874615857, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00015365703749231714, | |
| "eval_loss": 2.2552945613861084, | |
| "eval_runtime": 229.6151, | |
| "eval_samples_per_second": 11.937, | |
| "eval_steps_per_second": 5.971, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007682851874615857, | |
| "grad_norm": 1.953019380569458, | |
| "learning_rate": 5e-05, | |
| "loss": 2.1193, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0015365703749231714, | |
| "grad_norm": 2.05647873878479, | |
| "learning_rate": 0.0001, | |
| "loss": 1.9819, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0015365703749231714, | |
| "eval_loss": 1.7231560945510864, | |
| "eval_runtime": 236.8872, | |
| "eval_samples_per_second": 11.571, | |
| "eval_steps_per_second": 5.788, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0023048555623847574, | |
| "grad_norm": 1.9377185106277466, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.3919, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.003073140749846343, | |
| "grad_norm": 1.7036516666412354, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.103, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.003073140749846343, | |
| "eval_loss": 1.0012222528457642, | |
| "eval_runtime": 237.1483, | |
| "eval_samples_per_second": 11.558, | |
| "eval_steps_per_second": 5.781, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0038414259373079286, | |
| "grad_norm": 1.5257936716079712, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9302, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.004609711124769515, | |
| "grad_norm": 1.8204023838043213, | |
| "learning_rate": 5e-05, | |
| "loss": 0.9432, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.004609711124769515, | |
| "eval_loss": 0.9204530119895935, | |
| "eval_runtime": 237.1908, | |
| "eval_samples_per_second": 11.556, | |
| "eval_steps_per_second": 5.78, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0053779963122311, | |
| "grad_norm": 1.3599870204925537, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.8982, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.006146281499692686, | |
| "grad_norm": 1.5009428262710571, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.9569, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.006146281499692686, | |
| "eval_loss": 0.9022815823554993, | |
| "eval_runtime": 237.1346, | |
| "eval_samples_per_second": 11.559, | |
| "eval_steps_per_second": 5.782, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0069145666871542714, | |
| "grad_norm": 1.9179648160934448, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.8794, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.007682851874615857, | |
| "grad_norm": 1.1064144372940063, | |
| "learning_rate": 0.0, | |
| "loss": 0.885, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.007682851874615857, | |
| "eval_loss": 0.8971546292304993, | |
| "eval_runtime": 237.3849, | |
| "eval_samples_per_second": 11.547, | |
| "eval_steps_per_second": 5.775, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9247821240729600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |